Conv-Transformer Architecture for Unconstrained Off-LineUrdu Handwriting Recognition

Riaz, Nauman; Arbab, Haziq; Maqsood, Arooba; Nasir, Khuzaeymah Bin; Ul-Hasan, Adnan

doi:10.21203/rs.3.rs-1514700/v1

Cited by 3 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experiments were performed using a 1-dimensional Bi-Directional LSTM to classify individual character labels. Other works such as [35] use Transformer architectures with a CNN backbone for unconstrained character classification.…”

Section: Related Work a Urdu Handwritten Character Recognitionmentioning

confidence: 99%

“…The lack of properly structured and annotated data has always been a major hindrance for these types of tasks. Most recent methods [2], [35], [28] that involve the use of data-intensive and hungry architectures like LSTMs and Transformers usually are unable to perform when provided with sparse datasets. With continually changing styles and patterns, the Urdu language provides just that in the real world.…”

Section: Related Work a Urdu Handwritten Character Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

An Enhanced Prototypical Network Architecture for Few-Shot Handwritten Urdu Character Recognition

Sahay

Coustaty

2023

IEEE Access

View full text Add to dashboard Cite

Few shot models have started to gain a lot of popularity in the past few years. This is mostly because these models grant the ability to structure the representation space (classes) using a very less amount of examples for each class. Such models are usually trained on a wide range of different classes and their examples, which allows them to form and learn a decision-based metric in the process. Non-Latin languages, especially languages such as Urdu, have a bi-linear direction of writing and are context-sensitive in nature, and are hard to recognize. Also, unlike traditional English, there is a very small amount of clean, collated, and usable data that is available for the Urdu language. In this paper, we explore a prototypical network for k-shot classification on handwritten Urdu characters. The prototypical network learns the Euclidean embeddings of the provided images and uses clusters to classify newer examples. Our improved method is able to outperform other methods of few-shot learning and is able to accurately classify both Urdu characters as well as numerals using a minimal number of examples. After comprehensive qualitative and quantitative evaluation and comparison of our proposed approach with other methods to classify handwritten text in few-shot settings, we found out that our proposed approach was typically able to beat other methods by a margin of 1% − 2% while relying on a small training set.

show abstract

Section: Related Work a Urdu Handwritten Character Recognitionmentioning

confidence: 99%

Section: Related Work a Urdu Handwritten Character Recognitionmentioning

confidence: 99%

An Enhanced Prototypical Network Architecture for Few-Shot Handwritten Urdu Character Recognition

Sahay

Coustaty

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Here the output is the weighted sum of the value vector, where weight is computed using the softmax function. Attention is defined as shown in equation ( 2) (40).…”

Section: Vision Transformer Architecturementioning

confidence: 99%

Convolutional Vision Transformer for Handwritten Digit Recognition

Agrawal

Jagtap

2022

Preprint

View full text Add to dashboard Cite

Handwritten digit recognition is an essential step in understanding handwritten documents. The state-of-the-art convolutional neural networks (CNN) methods are mostly preferred for recognizing handwritten digits. Though the recognition accuracy is high, CNN filter weights don’t change even after training. Hence the process cannot adjust dynamically to changes in input. Recently the interest of researchers of computer vision has been on Vision Transformers (ViTs) and Multilayer Perceptrons (MLPs). The use of transformer architecture enabled substantial parallelization and translation quality improvement. The inadequacies of CNNs sparked a hybrid model revolution, which combines the best of both disciplines. This paper is written to view the impact of the hybrid model on handwritten digit recognition. The testing is done on the available benchmark datasets, the Extended Modified National institute of standards and technology (EMNIST) digits dataset, and the most significant historical handwritten digit dataset (DIDA). The 10-fold cross-validation accuracy achieved on EMNIST and DIDA is 99.89% and 99.73%, respectively. The results show that the proposed method achieves the highest accuracy compared to existing methodologies. The proposed method is robust, feasible, and effective on clean and uncleaned images.

show abstract

Performance analysis of hybrid deep learning framework using a vision transformer and convolutional neural network for handwritten digit recognition

Agrawal,

Jagtap,

Patil

et al. 2024

MethodsX

View full text Add to dashboard Cite

Conv-Transformer Architecture for Unconstrained Off-LineUrdu Handwriting Recognition

Cited by 3 publications

References 0 publications

An Enhanced Prototypical Network Architecture for Few-Shot Handwritten Urdu Character Recognition

An Enhanced Prototypical Network Architecture for Few-Shot Handwritten Urdu Character Recognition

Convolutional Vision Transformer for Handwritten Digit Recognition

Performance analysis of hybrid deep learning framework using a vision transformer and convolutional neural network for handwritten digit recognition

Contact Info

Product

Resources

About